Hi there, I have trained tesseract for urdu font, but there is an issue of spaces. Like when I test tesseract on my trained data, it gives correct output but is not space separated. Like it join two separate words and removes the space between them. i have attached sample output(capture .png) and sample image(capture1.png).
Capture.png :- https://www.dropbox.com/s/34r4cpdch2c7gz9/Capture.PNG?dl=0
Capture1.png :- https://www.dropbox.com/s/xiihkeyto4o4ml4/Capture1.PNG?dl=0
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi there, I have trained tesseract for urdu font, but there is an issue of spaces. Like when I test tesseract on my trained data, it gives correct output but is not space separated. Like it join two separate words and removes the space between them. i have attached sample output(capture .png) and sample image(capture1.png).
Capture.png :- https://www.dropbox.com/s/34r4cpdch2c7gz9/Capture.PNG?dl=0
Capture1.png :- https://www.dropbox.com/s/xiihkeyto4o4ml4/Capture1.PNG?dl=0
Since this is related to training, I suggest that you post your question in Tesseract's groups. You'd more likely get answers there.
https://groups.google.com/forum/#!forum/tesseract-ocr